Electric vehicle endurance mileage prediction and battery capacity management method and system

Through data collection, preprocessing and PID algorithm optimization model output, combined with battery health status monitoring and charging strategy optimization, the problems of insufficient range prediction accuracy and inaccurate battery capacity management are solved, and more efficient battery use and real-time optimization.

CN119078532AActive Publication Date: 2024-12-06CHINA FAW CO LTD +1

Patent Information

Application Number
CN202411145161.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-12-06
Estimated Expiration
2044-08-20

AI Technical Summary

Technical Problem

In the prior art, electric vehicles have insufficient range prediction accuracy and insufficient battery capacity management, and lack real-time optimization and adjustment mechanisms, which affect drivers' travel planning and battery usage efficiency.

Method used

Data collection and preprocessing are used, initial prediction model is constructed and model output is optimized through PID algorithm, combined with battery health status monitoring and charging strategy optimization, range prediction and battery capacity management are dynamically adjusted.

Benefits of technology

It improves the range prediction accuracy and battery usage efficiency of electric vehicles, provides real-time optimization and adjustment mechanisms, and enhances the ability to respond to multiple factors.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119078532A_ABST
    Figure CN119078532A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of vehicles, and discloses an electric vehicle endurance mileage prediction and battery capacity management method and system, electronic equipment, a storage medium and a vehicle, and the method comprises the steps: responding to vehicle operation data collected in real time, and carrying out the preprocessing of the operation data; in response to the preprocessed operation data, constructing an initial prediction model of the vehicle endurance mileage; dynamically adjusting the output of the initial prediction model based on a proportional element in a PI D algorithm so as to improve the prediction precision of the initial prediction model; adjusting the battery capacity based on the vehicle use data and the battery state data, including battery health state monitoring, battery capacity calibration, charging strategy optimization and battery use mode adjustment; and in combination with the optimized initial prediction model and the adjusted battery capacity information, calculating the current endurance mileage of the vehicle and outputting the current endurance mileage to a driver. According to the method, the endurance mileage prediction precision and the battery use efficiency of the electric vehicle can be effectively improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a method, system, electronic equipment, storage medium and vehicle for predicting the cruising range and managing the battery capacity of an electric vehicle. Background Art

[0002] At present, in the field of electric vehicles, the accurate calculation of driving range has always been a hot topic and difficulty in research. In the existing technology, prediction models based on statistical methods or machine learning algorithms are usually used to calculate the driving range of electric vehicles. These models mainly rely on the operating data of electric vehicles, such as speed, acceleration, battery voltage, etc., and predict future driving range by analyzing and processing these data.

[0003] In addition, for the management of battery capacity, the existing technology mainly monitors and adjusts it through the battery management system (BMS). BMS can detect the status and parameters of the battery in real time, including the battery's voltage, current, temperature, and SOC (State of Charge). Based on this information, BMS can control the battery's charge and discharge to ensure the battery's safety and performance.

[0004] The shortcomings of the existing technology mainly include the following aspects:

[0005] Insufficient range prediction accuracy: The range prediction models in existing technologies are often affected by multiple factors, such as road conditions, driving habits, ambient temperature, etc. These factors may cause a large deviation between the prediction results and the actual values, thus affecting the driver's travel planning.

[0006] Battery capacity management is not accurate enough: Although the BMS in the existing technology can perform basic monitoring and adjustment of the battery, it is still insufficient in optimizing and adjusting the battery capacity. The attenuation and change of battery capacity are affected by many factors, such as the number of charge and discharge cycles, operating temperature, etc. The existing technology often lacks comprehensive consideration of these factors, resulting in inaccurate battery capacity management.

[0007] Lack of real-time optimization and adjustment mechanism: The prediction models and battery management systems in existing technologies often lack real-time optimization and adjustment mechanisms. In actual use, the operating status and battery status of electric vehicles may change, and existing technologies often cannot respond and adjust to these changes in a timely manner, thus affecting the prediction accuracy and battery efficiency.

[0008] Therefore, the present application provides a method for predicting the range of an electric vehicle and managing the battery capacity to solve the above technical problems. Summary of the invention

[0009] The purpose of the present invention is to provide a method, system, electronic device, storage medium and vehicle for predicting the cruising range and managing the battery capacity of an electric vehicle, so as to solve the technical problems of low cruising range prediction accuracy and low battery utilization efficiency in the prior art.

[0010] In order to solve the above technical problems, the present invention provides a method for predicting the cruising range of an electric vehicle and managing the battery capacity, comprising:

[0011] A data collection and preprocessing step includes preprocessing the vehicle operation data in response to the vehicle operation data collected in real time, wherein the operation data includes vehicle usage data and battery status data;

[0012] The step of constructing an initial prediction model comprises constructing the initial prediction model of the vehicle's cruising range in response to the preprocessed operating data, wherein the initial prediction model is used to predict the vehicle's cruising range;

[0013] The initial prediction model optimization step includes dynamically adjusting the output of the initial prediction model based on the proportional link in the PID algorithm to improve the prediction accuracy of the initial prediction model;

[0014] A battery capacity optimization and adjustment step, comprising adjusting the battery capacity based on the vehicle usage data and the battery status data, including battery health status monitoring, battery capacity calibration, charging strategy optimization, and battery usage mode adjustment;

[0015] The cruising range calculation and output step includes combining the optimized initial prediction model and the adjusted battery capacity information to calculate the vehicle's current cruising range and output it to the driver.

[0016] In some specific embodiments, the data collection and preprocessing step includes preprocessing the vehicle operation data in response to the vehicle operation data collected in real time, wherein the operation data includes vehicle usage data and battery status data, and further includes:

[0017] The vehicle usage data includes driving speed, acceleration, slope and mileage;

[0018] The battery status data includes voltage, current, temperature and internal resistance;

[0019] The collected vehicle usage data and battery status data are cleaned and normalized to ensure the integrity and accuracy of the data.

[0020] In some specific embodiments, the step of constructing an initial prediction model includes constructing the initial prediction model of the vehicle's cruising range in response to the preprocessed operating data, wherein the initial prediction model is used to predict the vehicle's cruising range, and further includes:

[0021] Dividing the preprocessed running data into a training set and a test set for model training and verification;

[0022] Selecting a corresponding machine learning algorithm according to the prediction requirements and the characteristics of the operating data;

[0023] Using the data of the training set to train the machine learning algorithm, and constructing the initial prediction model, wherein the initial prediction model can predict the cruising range of the vehicle based on the input operation data;

[0024] The initial prediction model is evaluated using the data of the test set to verify the prediction accuracy and generalization ability of the initial prediction model.

[0025] In some specific embodiments, the initial prediction model optimization step includes dynamically adjusting the output of the initial prediction model based on the proportional link in the PID algorithm to improve the prediction accuracy of the initial prediction model, and further includes:

[0026] Dynamically adjusting the proportionality coefficient of the proportional link according to the error between the output of the initial prediction model calculated in real time and the actual driving situation;

[0027] Applying the adjusted proportional coefficient to the calculation formula of the proportional link to generate a new control amount;

[0028] The new control amount is applied to the initial prediction model, and the model output is adjusted in real time to improve the prediction accuracy.

[0029] In some specific embodiments, the battery capacity optimization and adjustment step includes adjusting the battery capacity based on the vehicle usage data and the battery status data, including battery health status monitoring, battery capacity calibration, charging strategy optimization, and battery usage mode adjustment, and further includes:

[0030] Monitor key indicators in the battery status data and evaluate the battery health status;

[0031] Based on the changes in power recorded during the complete charge and discharge process, the actual battery capacity is calculated to calibrate the battery capacity;

[0032] Optimize charging strategy and adjust charging parameters based on the current battery status data and usage requirements;

[0033] Based on the vehicle usage data and battery characteristics, the vehicle battery usage mode is adjusted to extend the battery life.

[0034] In some specific embodiments, the cruising range calculation and output step includes combining the optimized initial prediction model and the adjusted battery capacity information to calculate the current cruising range of the vehicle and output it to the driver, further including:

[0035] Calculate the current cruising range of the vehicle by combining the optimized initial prediction model and the adjusted battery capacity information;

[0036] The calculated cruising range information is presented to the driver in a visual or interactive manner.

[0037] Based on the same concept, the present invention also provides an electric vehicle range prediction and battery capacity management system, comprising:

[0038] a data collection and preprocessing module, configured to preprocess the vehicle operation data in response to the vehicle operation data collected in real time, wherein the operation data includes vehicle usage data and battery status data;

[0039] An initial prediction model building module is configured to build the initial prediction model of the vehicle's cruising range in response to the preprocessed operating data, wherein the initial prediction model is used to predict the vehicle's cruising range;

[0040] An initial prediction model optimization module is configured to dynamically adjust the output of the initial prediction model based on a proportional link in a PID algorithm to improve the prediction accuracy of the initial prediction model;

[0041] A battery capacity optimization and adjustment module, configured to adjust the battery capacity based on the vehicle usage data and the battery status data, including battery health status monitoring, battery capacity calibration, charging strategy optimization, and battery usage mode adjustment;

[0042] The cruising range calculation and output module is configured to combine the optimized initial prediction model and the adjusted battery capacity information to calculate the vehicle's current cruising range and output it to the driver.

[0043] Based on the same concept, the present invention also provides an electronic device, including: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the electric vehicle range prediction and battery capacity management method.

[0044] Based on the same concept, the present invention also provides a computer-readable storage medium, which stores a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the electric vehicle range prediction and battery capacity management method.

[0045] Based on the same concept, the present invention also provides a vehicle, wherein the vehicle is provided with the electric vehicle range prediction and battery capacity management system as described above.

[0046] Compared with the prior art, the invention has the following beneficial effects:

[0047] The present invention discloses a method, system, electronic equipment, storage medium and vehicle for predicting the cruising range and managing the battery capacity of an electric vehicle, which can effectively improve the prediction accuracy of the cruising range of the electric vehicle and the battery use efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flowchart of some specific embodiments of a method for predicting the cruising range and managing the battery capacity of an electric vehicle according to the present invention;

[0049] Figure 2 It is a schematic diagram of a PID algorithm in some applications of a method for predicting the cruising range and managing the battery capacity of an electric vehicle according to the present invention;

[0050] Figure 3 It is a schematic diagram of the structure of an electric vehicle cruising range prediction and battery capacity management system in some specific embodiments of the present invention;

[0051] Figure 4 It is a structural schematic diagram of an electronic device of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0053] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings, and "multiple" generally includes at least two.

[0054] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0055] It should be understood that although the terms first, second, third, etc. may be used to describe in the embodiments of the present application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0056] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.

[0057] It should also be noted that the term "includes", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, so that a commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprising a ..." do not exclude the existence of other identical elements in the commodity or device including the elements.

[0058] It should be particularly noted that any symbols and / or numbers in the specification that are not marked in the accompanying drawings are not drawing marks.

[0059] Reference Figure 1 , a method for predicting the range of an electric vehicle and managing the battery capacity, comprising:

[0060] S101, a data collection and preprocessing step, comprising preprocessing the vehicle operation data in response to the vehicle operation data collected in real time, wherein the operation data includes vehicle usage data and battery status data;

[0061] In some of these applications, the data collection and preprocessing steps include preprocessing the operation data in response to the vehicle operation data collected in real time, the operation data including vehicle usage data and battery status data, the vehicle usage data including driving speed, acceleration, slope and mileage; the battery status data including voltage, current, temperature and internal resistance; and cleaning and normalizing the collected vehicle usage data and battery status data to ensure the integrity and accuracy of the data.

[0062] It is understood that real-time capture of operating data from the electric vehicle's sensor network (such as speed sensor, acceleration sensor, slope sensor, odometer, etc.) and battery management system (BMS). Connecting with sensors and BMS through standard CAN bus, LIN bus or dedicated interface ensures the real-time and accuracy of data. Real-time collection of vehicle speed (such as current speed 50km / h), acceleration (such as acceleration change rate 0.5m / s 2 ), slope (such as the current driving slope of 5%) and mileage (such as the cumulative mileage of 1000km). Simultaneously collect the battery voltage (such as the current voltage of 330V), current (such as the discharge current of 100A), temperature (such as the battery temperature of 25℃) and internal resistance (such as the current internal resistance of 50mΩ). By setting reasonable thresholds (such as the speed does not exceed the legal speed limit of 120km / h, the acceleration change rate does not exceed ±3m / s 2 , the temperature does not exceed the normal operating range of the battery -20℃ to 60℃, etc.), identify and remove abnormal values. For example, when the speed data is detected to be 200km / h, it is judged as abnormal and removed. For missing values ​​caused by sensor failure or data transmission problems, forward filling, backward filling or interpolation methods (such as linear interpolation, polynomial interpolation, etc.) are used to complete them.

[0063] In order to eliminate the influence of different dimensions and ranges on data processing and improve the convergence speed and prediction accuracy of the model, the Min-Max Scaling method is used to convert the data into the range of 0 to 1. The specific formula is:

[0064]

[0065] Among them, x is the original data, x min and x max are the minimum and maximum values ​​in the data set, respectively, and x norm is the normalized data.

[0066] For example, for the battery voltage data, assuming that its minimum value is 200V, the maximum value is 400V, and the current voltage is 330V, the normalized voltage is:

[0067]

[0068] The cleaned and normalized data can be stored in the database.

[0069] S102, a step of constructing an initial prediction model, comprising constructing the initial prediction model of the vehicle's cruising range in response to the preprocessed operating data, wherein the initial prediction model is used to predict the vehicle's cruising range;

[0070] In some of the applications, the step of constructing an initial prediction model includes constructing an initial prediction model for the vehicle's range in response to the preprocessed operating data, the initial prediction model being used to predict the vehicle's range, dividing the preprocessed operating data into a training set and a test set for model training and verification; selecting a corresponding machine learning algorithm based on the prediction requirements and the characteristics of the operating data; training the machine learning algorithm using the data in the training set to construct an initial prediction model, the initial prediction model being able to predict the vehicle's range based on the input operating data; and evaluating the initial prediction model using the data in the test set to verify the prediction accuracy and generalization ability of the initial prediction model.

[0071] It is understandable that the pre-processed operating data (including vehicle usage data and battery status data) is randomly divided into two parts according to a certain ratio (such as 70% training set, 30% test set). According to the prediction requirements (i.e. predicting the vehicle's range) and the characteristics of the operating data (such as time series, nonlinear relationship, etc.), a machine learning algorithm is selected. Common algorithms include linear regression, decision tree, random forest, gradient boosting tree (GBDT), neural network, etc.

[0072] For example, considering that vehicle range prediction may involve complex relationships between multiple variables, the gradient boosting tree (GBDT) was selected as the initial algorithm because it is good at handling nonlinear relationships and capturing the interaction effects between variables.

[0073] The selected machine learning algorithm is trained using the data from the training set. During the training process, the algorithm learns based on the input operating data (such as driving speed, acceleration, slope, mileage, battery voltage, current, temperature, internal resistance, etc.) and the corresponding range labels to establish a mapping relationship between input and output.

[0074] For example, in GBDT model training, multiple decision trees are constructed through continuous iterations, and each tree attempts to correct the prediction error of the previous tree, eventually forming a strong learner for predicting the vehicle's range.

[0075] The trained initial prediction model is evaluated using the data from the test set to verify its prediction accuracy and generalization ability.

[0076] For example, we select the root mean square error (RMSE) as the evaluation indicator and calculate the RMSE value between the actual mileage on the test set and the mileage predicted by the model. If the RMSE value is small, it means that the model prediction accuracy is high; if the RMSE value on the test set is similar to or slightly higher than that on the training set, it means that the model generalization ability is good.

[0077] According to the evaluation results, the model is adjusted and optimized, including adjusting algorithm parameters, changing algorithms, adding feature engineering (such as feature selection, feature transformation), etc., to improve the prediction accuracy and generalization ability of the model.

[0078] For example, if the RMSE value of the initial GBDT model is high, you can try to adjust parameters such as the tree depth and learning rate, or introduce more relevant features (such as weather conditions, driver habits, etc.) to obtain better prediction results.

[0079] S103, an initial prediction model optimization step, including dynamically adjusting the output of the initial prediction model based on a proportional link in a PID algorithm to improve the prediction accuracy of the initial prediction model;

[0080] In some of these applications, the initial prediction model optimization step includes dynamically adjusting the output of the initial prediction model based on the proportional link in the PID algorithm to improve the prediction accuracy of the initial prediction model; dynamically adjusting the proportional coefficient of the proportional link according to the error between the output of the initial prediction model calculated in real time and the actual driving condition; applying the adjusted proportional coefficient to the calculation formula of the proportional link to generate a new control quantity; applying the new control quantity to the initial prediction model, and adjusting the model output in real time to improve the prediction accuracy.

[0081] It can be understood that the proportional link in the PID control algorithm is initialized and an initial proportional coefficient Kp is set to preliminarily adjust the deviation between the model output and the actual value. The actual driving data of the vehicle is collected in real time, the output of the initial prediction model is compared with the actual driving data, and the error E(t) between the two is calculated. The error E(t) can be defined as:

[0082] E(t)=Yactual(t)-Ypredicted(t)

[0083] Among them, Yactual(t) represents the actual driving data at time t, and Ypredicted(t) represents the predicted output of the model at time t.

[0084] According to the size and direction of the error E(t), analyze the nature of the error (such as positive deviation, negative deviation, deviation size, etc.).

[0085] Based on the error analysis results, dynamically adjust the proportional coefficient Kp. When the error is large, increase the value of Kp to speed up the adjustment; when the error is small, reduce the value of Kp to avoid over-adjustment. The specific adjustment formula can be:

[0086] Kp new =Kp old +α·sign(E(t))·|E(t)| β

[0087] Among them, α is the learning rate, which controls the adjustment amplitude; β is the adjustment factor, which affects the sensitivity of the error size to the Kp adjustment; sign(E(t)) is the sign function used to determine the adjustment direction.

[0088] The adjusted proportional coefficient Kp new Applied to the calculation formula of the proportional link, recalculate the control quantity U(t):

[0089] U(t)=Kp new ·E(t)

[0090] U(t) is the new control variable and will be used to adjust the output of the initial prediction model.

[0091] The new control quantity U(t) is applied to the initial prediction model. By modifying the internal parameters or calculation process of the model, the output of the model is adjusted in real time to reduce the error between the model output and the actual driving data, thereby improving the prediction accuracy.

[0092] The scale factor is adjusted dynamically according to real-time data to optimize the output of the prediction model. Through multiple iterations, the optimal scale factor can be gradually approached, which significantly improves the accuracy of the prediction model.

[0093] S104, a battery capacity optimization and adjustment step, comprising adjusting the battery capacity based on the vehicle usage data and the battery status data, including battery health status monitoring, battery capacity calibration, charging strategy optimization, and battery usage mode adjustment;

[0094] In some of these applications, the battery capacity optimization and adjustment steps include adjusting the battery capacity based on vehicle usage data and battery status data, including battery health status monitoring, battery capacity calibration, charging strategy optimization and battery usage mode adjustment, monitoring key indicators in the battery status data and evaluating the battery health status; calculating the actual battery capacity based on the power changes recorded during the complete charge and discharge process to calibrate the battery capacity; optimizing the charging strategy and adjusting the charging parameters based on the current battery status data and usage requirements; adjusting the vehicle battery usage mode based on the vehicle usage data and battery characteristics to extend the battery life.

[0095] It is understandable that the key indicators in the battery status data are continuously monitored, including but not limited to battery voltage, current, temperature, internal resistance, and number of charge and discharge cycles.

[0096] For example, after a charge and discharge cycle, the internal resistance of the battery increases by 5mΩ compared with the previous one, and the temperature peak exceeds the recommended 45°C, indicating a decline in the battery's health status.

[0097] Based on the charge changes recorded during the complete charge and discharge process, the actual battery capacity is calculated and compared with the nominal capacity to perform battery capacity calibration.

[0098] Based on the current battery status data (such as health status, remaining power, temperature, etc.) and user usage requirements (such as expected mileage, charging time preference, etc.), the charging strategy is optimized and charging parameters such as charging current, voltage, time, etc. are adjusted.

[0099] For example, if the current battery temperature is monitored to be 25°C, the remaining power is 20%, and the user plans to fully charge the battery within 2 hours for a long-distance trip, the charging strategy will be automatically adjusted to adopt the fast charging mode, charging with a higher current and voltage, while ensuring that the battery temperature is within a safe range.

[0100] Based on vehicle usage data (such as driving speed, acceleration and deceleration frequency, road condition information, etc.) and battery characteristics (such as energy density, charging and discharging efficiency, etc.), adjust the vehicle battery usage mode, such as energy recovery intensity, power output strategy, etc., to reduce unnecessary battery loss and extend battery life.

[0101] For example, when driving on congested urban roads, the energy recovery system is increased in terms of frequent starting and stopping and low-speed driving characteristics to convert braking energy into electrical energy for storage. At the same time, the power output strategy is adjusted to reduce the number of rapid acceleration and deceleration to reduce the number of high-current discharge and charging of the battery, thereby protecting the battery and extending its service life.

[0102] S105, a cruising range calculation and output step, includes combining the optimized initial prediction model and the adjusted battery capacity information to calculate the vehicle's current cruising range and output it to the driver.

[0103] In some of these applications, the range calculation and output steps include calculating the vehicle's current range and outputting it to the driver by combining the optimized initial prediction model and the adjusted battery capacity information, calculating the vehicle's current range by combining the optimized initial prediction model and the adjusted battery capacity information; and presenting the calculated range information to the driver in a visual or interactive manner.

[0104] It can be understood that the optimized initial prediction model is combined with the adjusted battery capacity information to calculate the remaining range of the vehicle in the current state according to the current vehicle driving state (such as speed, acceleration, load, etc.) and external environmental conditions.

[0105] For example, the vehicle is currently traveling at a constant speed of 60km / h on a flat road, the outside temperature is 20°C, and the battery SOC is 70% (i.e., the remaining power is 58kWh*70%=40.6kWh). The optimized prediction model calculates the remaining range of the vehicle under current conditions based on these parameters, combined with the vehicle's power system efficiency and drag coefficient, to be approximately 350km.

[0106] The calculated range information is presented to the driver in a visual or interactive way, through the vehicle display, such as a digital display on the dashboard, a graphical interface, or voice prompts.

[0107] For example, on the in-car display, the range information is displayed in digital form on the main interface, accompanied by a graphical representation (such as a battery bar or a range map). The driver can also interact through the touch screen or voice commands to query more detailed range information or adjust related settings. In addition, an early warning prompt is issued based on the remaining power and estimated mileage, reminding the driver to charge in time or adjust the trip plan.

[0108] Combine the following Figure 2 The following are some examples of the electric vehicle range prediction and battery capacity management method of the present invention in some applications:

[0109] In the PID algorithm, the proportional link (P link) directly generates the control amount according to the error signal. This embodiment collects vehicle usage data in real time and dynamically adjusts the proportional coefficient of the P link in combination with the current battery status to adapt to different driving conditions and battery status, thereby improving the accuracy of the cruising range calculation. The calculation formula is as follows:

[0110] The calculation formula of the P link is: P = K_p*e(t), where:

[0111] (P) is the output of the P link.

[0112] (K_p) is the proportional coefficient, which is an adjustable parameter and needs to be adjusted according to actual conditions.

[0113] (e(t)) is the error at the current moment, that is, the difference between the expected output and the actual output.

[0114] In the range calculation of an electric vehicle, (e(t)) can be the difference between the expected range and the actual range.

[0115] Optimization and adjustment of battery capacity:

[0116] The calculation formula of battery capacity (C) is based on the nominal capacity and current state of the battery. In this embodiment, it is adjusted according to the real-time state and usage data of the battery. Here, it is simplified as: C_actual = C_rated*f(S, H, T, ...)

[0117] in:

[0118] C_actual is the actual capacity of the battery.

[0119] C_rated is the nominal capacity of the battery.

[0120] f(S, H, T, ...) is an adjustment function that adjusts the battery capacity according to factors such as the battery state ((S)), historical data ((H)), and temperature ((T)).

[0121] Battery health status monitoring: BMS detects key battery indicators such as internal resistance and capacity decay rate in real time to evaluate the battery health status.

[0122] Battery capacity calibration: Regularly calibrate the battery capacity, record the power changes through a complete charge and discharge process, and obtain accurate battery capacity data.

[0123] Charging strategy optimization: Optimize the charging strategy based on the current battery status and usage requirements, such as using fast charging or slow charging mode, and adjusting the charging current and voltage.

[0124] Battery usage mode adjustment: Adjust the usage mode of electric vehicles according to the battery type and characteristics, such as avoiding use in extreme temperature environments and optimizing driving speed and acceleration and deceleration frequency.

[0125] Range calculation and output: Combine the optimized prediction model and battery capacity information to calculate the current range of the electric vehicle and output it to the driver or related systems through the vehicle display or mobile phone APP. The specific calculation is as follows:

[0126] The calculation formula for the cruising range (R) can be based on the current charge Q_current and the actual battery capacity C_actual: R = (Q_current / E_avg)*C_actual

[0127] in:

[0128] (R) is the estimated range.

[0129] (C_actual) is the current battery charge.

[0130] (E_avg) is the average energy consumption of electric vehicles, estimated based on historical driving data and current driving conditions;

[0131] In practical applications, PID algorithm and battery capacity optimization complement each other. PID algorithm adjusts the output to reduce the error (i.e. the prediction error of the driving range), while battery capacity optimization provides more accurate battery capacity information, making the prediction of driving range more accurate.

[0132] This embodiment is described below in conjunction with application scenarios:

[0133] The sensors used in this embodiment include speed sensors, current sensors, temperature sensors, etc., which can meet the needs of real-time data collection of electric vehicles.

[0134] Battery Management Unit (BMU):

[0135] The BMU is one of the key components in electric vehicles, responsible for real-time monitoring and management of the battery status. The BMU used in this embodiment has the characteristics of high precision, high reliability and fast response, and can accurately predict the attenuation of battery capacity and make corrections.

[0136] Energy consumption model:

[0137] The energy consumption model is one of the key factors in predicting the range of electric vehicles. The energy consumption model used in this embodiment is established based on a large amount of experimental data and actual driving experience, and can accurately estimate the energy consumption of electric vehicles under different environmental conditions.

[0138] PID algorithm:

[0139] In this embodiment, the PID algorithm is used to optimize the accuracy of the range prediction by continuously adjusting the PID parameters to reduce the error and find the best parameter combination.

[0140] like Figure 2 As shown:

[0141] The PID algorithm adjusts the output of the controller through three parts: proportional, integral and differential, so that the electric vehicle can calculate the accurate range under different conditions.

[0142] Proportional part: The proportional device generates a control amount based on the current error

[0143] Error definition: Set the expected cruising range to P target , the actual cruising range is P actual , then the error e(t) is defined as:

[0144] e(t)=P target -P actual

[0145] Proportional term calculation: Proportional gain K p Multiply by the current error to generate the proportional control amount.

[0146] Proportionalterm=K p ·e(t)

[0147] The proportional term allows the system to respond quickly. When the expected deviation from the target value is large, a larger control amount is output to quickly adjust the range calculation.

[0148] Integral part: The integral controller accumulates historical errors to eliminate the static errors of the system and ensure that the system can stably operate the calculated results near the actual cruising range.

[0149] The integral term accumulates historical errors to counteract the situation where the system deviates from the actual cruising range for a long time.

[0150]

[0151] Among them, K i is the integral gain.

[0152] Derivative part: The derivative controller predicts future trends based on the error change rate and adjusts the control output accordingly to improve the stability and response speed of the system.

[0153] The derivative term predicts future errors by measuring the rate of change of the range error.

[0154]

[0155] The outputs of the three parts are weighted and summed to obtain the final PID control output, which is used to adjust the range output of the electric vehicle, thereby calculating the accurate range.

[0156]

[0157] The following real-time data is obtained through the vehicle-mounted sensors: Current battery capacity C current , current ambient temperature T, power consumption value P in the last 25 km avg25 , current wind speed V wind , current altitude A, current vehicle speed V car , input the above parameters into the adjustment function f(C current , T, P avg25 , V wind , V car , ...), output the calculated cruising range P target, bring the cruising range into the PID controller and set the initial PID parameters: proportional gain K p =0.5; integral gain K i =0.02; differential gain K d =0.1; During the control process and the experimental stage, the initial parameters are continuously adjusted according to the output results, and finally the gain parameters after stable output are obtained.

[0158] For the method steps disclosed in the above embodiments, the method steps are described as a series of action combinations for the purpose of simple description, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0159] like Figure 3 As shown, the present invention also provides an electric vehicle range prediction and battery capacity management system, comprising:

[0160] The data collection and preprocessing module 201 is configured to preprocess the vehicle operation data collected in real time in response to the operation data, wherein the operation data includes vehicle usage data and battery status data;

[0161] An initial prediction model building module 202 is configured to build the initial prediction model of the vehicle cruising range in response to the preprocessed operating data, wherein the initial prediction model is used to predict the vehicle cruising range;

[0162] The initial prediction model optimization module 203 is configured to dynamically adjust the output of the initial prediction model based on the proportional link in the PID algorithm to improve the prediction accuracy of the initial prediction model;

[0163] A battery capacity optimization and adjustment module 204, configured to adjust the battery capacity based on the vehicle usage data and the battery status data, including battery health status monitoring, battery capacity calibration, charging strategy optimization, and battery usage mode adjustment;

[0164] The cruising range calculation and output module 205 is configured to combine the optimized initial prediction model and the adjusted battery capacity information to calculate the current cruising range of the vehicle and output it to the driver.

[0165] It is worth noting that although only some basic functional modules are disclosed in the embodiments of the present invention, it does not mean that the composition of the present system is limited to the above basic functional modules. On the contrary, what the present embodiment wants to express is that on the basis of the above basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. In other words, the present system is open rather than closed. Just because the present embodiment only discloses individual basic functional modules, it cannot be considered that the protection scope of the claims of the present invention is limited to the disclosed basic functional modules. At the same time, for the convenience of description, the above devices are described in terms of functions and are described separately in various units and modules. Of course, when implementing the present invention, the functions of each unit and module can be implemented in the same or one or more software and / or hardware.

[0166] like Figure 4 As shown, the present invention also provides an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the electric vehicle range prediction and battery capacity management method.

[0167] Figure 4 Schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 The electronic device provided in the embodiment of the present invention includes: one or more processors 710 and a storage device 720; the processor 710 in the electronic device may be one or more, Figure 4 A processor 710 is taken as an example; the storage device 720 is used to store one or more programs; the one or more programs are executed by the one or more processors 710, so that the one or more processors 710 implement the electric vehicle range prediction and battery capacity management method as described in any one of the embodiments of the present invention.

[0168] The electronic device may further include: an input device 730 and an output device 740 .

[0169] The processor 710, storage device 720, input device 730 and output device 740 in the electronic device can be connected via a bus or other means. Figure 4 The example of connecting through bus is taken in the following.

[0170] The storage device 720 in the electronic device is a computer-readable storage medium that can be used to store one or more programs, which can be software programs, computer executable programs and modules, such as program instructions / modules corresponding to the electric vehicle range prediction and battery capacity management method provided in the embodiment of the present invention. The processor 710 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the storage device 720, that is, the electric vehicle range prediction and battery capacity management method in the above method embodiment is implemented.

[0171] The storage device 720 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the storage device 720 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the storage device 720 may further include a memory remotely arranged relative to the processor 710, and these remote memories may be connected to the device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0172] The input device 730 may be used to receive input digital or character information and generate key signal input related to user settings and function control of the electronic device. The output device 740 may include a display device such as a display screen.

[0173] The present invention also provides a computer-readable storage medium storing a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the electric vehicle range prediction and battery capacity management method.

[0174] Specifically, the computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0175] The present invention also provides a vehicle, wherein the vehicle is provided with the electric vehicle range prediction and battery capacity management system as described above.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting the range of electric vehicles and managing battery capacity. It is characterized in that include: A data collection and preprocessing step includes preprocessing the vehicle operation data in response to the vehicle operation data collected in real time, wherein the operation data includes vehicle usage data and battery status data; The step of constructing an initial prediction model comprises constructing the initial prediction model of the vehicle's cruising range in response to the preprocessed operating data, wherein the initial prediction model is used to predict the vehicle's cruising range; The initial prediction model optimization step includes dynamically adjusting the output of the initial prediction model based on the proportional link in the PID algorithm to improve the prediction accuracy of the initial prediction model; A battery capacity optimization and adjustment step, comprising adjusting the battery capacity based on the vehicle usage data and the battery status data, including battery health status monitoring, battery capacity calibration, charging strategy optimization, and battery usage mode adjustment; The cruising range calculation and output step includes combining the optimized initial prediction model and the adjusted battery capacity information to calculate the vehicle's current cruising range and output it to the driver.

2. The electric vehicle range prediction and battery capacity management method according to claim 1, It is characterized in that The data collection and preprocessing step includes preprocessing the vehicle operation data in response to the vehicle operation data collected in real time, wherein the operation data includes vehicle usage data and battery status data, and further includes: The vehicle usage data includes driving speed, acceleration, slope and mileage; The battery status data includes voltage, current, temperature and internal resistance; The collected vehicle usage data and battery status data are cleaned and normalized to ensure the integrity and accuracy of the data.

3. The electric vehicle range prediction and battery capacity management method according to claim 1, It is characterized in that The step of constructing an initial prediction model includes constructing the initial prediction model of the vehicle's cruising range in response to the preprocessed operating data, wherein the initial prediction model is used to predict the vehicle's cruising range, and further includes: Dividing the preprocessed running data into a training set and a test set for model training and verification; Selecting a corresponding machine learning algorithm according to the prediction requirements and the characteristics of the operating data; Using the data of the training set to train the machine learning algorithm, and constructing the initial prediction model, wherein the initial prediction model can predict the cruising range of the vehicle based on the input operation data; The initial prediction model is evaluated using the data of the test set to verify the prediction accuracy and generalization ability of the initial prediction model.

4. The electric vehicle range prediction and battery capacity management method according to claim 1, It is characterized in that The initial prediction model optimization step includes dynamically adjusting the output of the initial prediction model based on the proportional link in the PID algorithm to improve the prediction accuracy of the initial prediction model, and further includes: Dynamically adjusting the proportionality coefficient of the proportional link according to the error between the output of the initial prediction model calculated in real time and the actual driving situation; Applying the adjusted proportional coefficient to the calculation formula of the proportional link to generate a new control amount; The new control amount is applied to the initial prediction model, and the model output is adjusted in real time to improve the prediction accuracy.

5. The electric vehicle range prediction and battery capacity management method according to claim 1, It is characterized in that The battery capacity optimization and adjustment step includes adjusting the battery capacity based on the vehicle usage data and the battery status data, including battery health status monitoring, battery capacity calibration, charging strategy optimization, and battery usage mode adjustment, and further includes: Monitor key indicators in the battery status data and evaluate the battery health status; Based on the changes in power recorded during the complete charge and discharge process, the actual battery capacity is calculated to calibrate the battery capacity; Optimize charging strategy and adjust charging parameters based on the current battery status data and usage requirements; Based on the vehicle usage data and battery characteristics, the vehicle battery usage mode is adjusted to extend the battery life.

6. The electric vehicle range prediction and battery capacity management method according to claim 1, It is characterized in that The cruising range calculation and output step includes combining the optimized initial prediction model and the adjusted battery capacity information to calculate the current cruising range of the vehicle and output it to the driver, further including: Calculate the current cruising range of the vehicle by combining the optimized initial prediction model and the adjusted battery capacity information; The calculated cruising range information is presented to the driver in a visual or interactive manner.

7. An electric vehicle range prediction and battery capacity management system, It is characterized in that include: a data collection and preprocessing module, configured to preprocess the vehicle operation data in response to the vehicle operation data collected in real time, wherein the operation data includes vehicle usage data and battery status data; An initial prediction model building module is configured to build the initial prediction model of the vehicle's cruising range in response to the preprocessed operating data, wherein the initial prediction model is used to predict the vehicle's cruising range; An initial prediction model optimization module is configured to dynamically adjust the output of the initial prediction model based on the proportional link in the PID algorithm to improve the prediction accuracy of the initial prediction model; A battery capacity optimization and adjustment module, configured to adjust the battery capacity based on the vehicle usage data and the battery status data, including battery health status monitoring, battery capacity calibration, charging strategy optimization, and battery usage mode adjustment; The cruising range calculation and output module is configured to combine the optimized initial prediction model and the adjusted battery capacity information to calculate the vehicle's current cruising range and output it to the driver.

8. An electronic device, It is characterized in that include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the method described in any one of claims 1 to 6.

9. A computer-readable storage medium, It is characterized in that It stores a computer program executable by an electronic device, and when the computer program runs on the electronic device, the electronic device executes the steps of the method described in any one of claims 1 to 6.

10. A vehicle, It is characterized in that The vehicle is provided with the electric vehicle range prediction and battery capacity management system as claimed in claim 7.

Citation Information

Patent Citations

  • Vehicle driving range calculation self-adapting method and device and vehicle

    CN107009912A

  • Calculation method for calibrating PACKSOC based on capacity of single battery

    CN111239611A

  • Electric vehicle endurance mileage prediction method

    CN114091735A

  • Fuel cell vehicle battery optimization management method, system, equipment and medium

    CN114122466A

  • Vehicle endurance mileage prediction method and device, equipment and storage medium

    CN114274780A

Cited By

  • Vehicle endurance mileage determination method and device, equipment, storage medium and product

    CN119858452A